Important
Course website: https://performanceestimation.github.io/Tutorial-SMAI-MODE/
SMAI-MODE: https://mode2026.sciencesconf.org/
Dates: starts March 16th, 2026 at 2pm, ends March 17th, 2026 at 6pm. About 6 * 90mins.
Takes place at: Valrose campus (Université Côte d'Azur), J. A. Dieudonné laboratory.
Adress: Parc Valrose, 28 Avenue Valrose, 06000 Nice (maps)
Transport: Tram T1 (stop at Valrose/Université), Bus 11, 16, 37
Performance estimation problems were introduced in 2014 by Yoel Drori and Marc Teboulle, see [1]. In this mini-class, we mostly follows the perspective and formalism and developments from [2, 3]. A friendly informal introduction to this formalism is available in this blog post.
We thank Daniel Berg Thomsen for numerous feedback on the content of this mini-course.
We also thank Damine Ngo for his work on building the tutorial UI.
Our projects were co-funded by the European Research Council (ERC grants SEQUOIA 724063 and CASPER 101162889) and under the management of Agence Nationale de la Recherche (ANR-19-CHIA-0002-01/chaire SCAI and Hi!Paris and ANR-23-IACL-0008 PR[AI]RIE-PSAI). Views and opinions expressed are however those of the authors only.
|
|
|
[1] Y. Drori, M. Teboulle (2014). Performance of first-order methods for smooth convex minimization: a novel approach. Mathematical Programming 145(1–2), 451–482.
[2] A. Taylor, J. Hendrickx, F. Glineur (2017). Smooth strongly convex interpolation and exact worst-case performance of first-order methods. Mathematical Programming, 161(1-2), 307-345.
[3] A. Taylor, J. Hendrickx, F. Glineur (2017). Exact worst-case performance of first-order methods for composite convex optimization. SIAM Journal on Optimization, 27(3):1283–1313.